© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8866
    Prev
    Next
    INDEX
    Explanations

    the word "respect" and perhaps a few related words

    oai_token-act-pair · gemini-2.0-flash

    the term 'respect'

    np_token-act-pair-logits · gpt-4o-mini

    respect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ")"
    -0.58
    مك
    -0.52
    folger
    -0.51
     ")");
    -0.51
    ábado
    -0.50
    enscha
    -0.50
    랜드
    -0.49
    rdom
    -0.48
     ")";
    -0.46
    destruct
    -0.46
    POSITIVE LOGITS
     to
    0.95
    bootstrapcdn
    0.72
    tagHelperRunner
    0.65
    <bos>
    0.58
     InputDecoration
    0.57
    msgTypes
    0.57
    UnsafeEnabled
    0.55
    tothe
    0.54
    المكان
    0.54
     Réponses
    0.54
    Activations Density 4.747%

    No Known Activations